© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3048
    Prev
    Next
    INDEX
    Explanations

    doing a good job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $};
    1.48
    =\{\
    1.48
    いる
    1.47
     производителей
    1.47
    🧸
    1.45
     ""))
    1.43
     "":
    1.42
    yu
    1.42
    apatt
    1.40
    (\
    1.38
    POSITIVE LOGITS
    帼
    1.65
    íme
    1.55
    aimanapun
    1.46
     собой
    1.27
    ievements
    1.26
    Succ
    1.24
    underset
    1.23
     stance
    1.23
    ə
    1.22
    を果た
    1.21
    Activations Density 0.009%

    No Known Activations